Compare models

Pick up to 4models. Specs render side-by-side. Share the URL — it's stateless.

Comparing agents instead? Switch to agent compare →

Selected

Claude 4.7 Opus×

Claude 4.6 Sonnet×

DeepSeek-R1×

GPT-5×Clear all

	Claude 4.7 Opus Anthropic	Claude 4.6 Sonnet Anthropic	DeepSeek-R1 DeepSeek	GPT-5 OpenAI
Vendor	Anthropic	Anthropic	DeepSeek	OpenAI
Family	Claude	Claude	DeepSeek	GPT
Release date	2026-04-16	2026-02-17	2025-01-20	2025-08-07
Context window	1,000,000 tokens	1,000,000 tokens	128,000 tokens	400,000 tokens
Parameters	—	—	671B	—
Modality	text, vision	text, vision	text	text, vision, audio
License	proprietary	proprietary	MIT	proprietary
Source	proprietary	proprietary	open weights	proprietary
Description	Anthropic's previous Opus flagship — superseded by Opus 4.8 on May 28, 2026 (42-day cycle). Optimized for complex reasoning and coding. Improved software engineering, long-running coding tasks, and higher-resolution vision over Claude 4.6.	Anthropic's mid-tier flagship — released 12 days after Opus 4.6 and matching most of its capabilities at ~40% the API cost ($3/$15 per 1M tokens). 1M-token context.	Reasoning-focused open-weight model.	OpenAI's flagship general-purpose model. Superseded by GPT-5.5 in April 2026.
Links	vendor →		weights →	vendor →
Benchmarks
MMLU-Pro	88.2%	85.4%	—	85.1%
GPQA-D	90.1%	85.8%	—	87.3%
HumanEval	97.4%	95.9%	—	95.2%
Aider	91.2%	83.6%	—	85.4%
AIME-25	93.5%	87.4%	79.8%	91.0%
LiveCB	80.2%	73.8%	—	74.5%
MMMU	79.0%	—	—	74.1%